© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 12031
    Prev
    Next
    INDEX
    Explanations

    time-related expressions, specifically related to the concept of days

    oai_token-act-pair · gpt-3.5-turbo

    phrases referring to durations expressed in days

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.80
    emale
    -0.78
    emort
    -0.78
    acus
    -0.75
    inav
    -0.75
    umbn
    -0.74
    acted
    -0.70
    icidal
    -0.68
    ilde
    -0.66
    INC
    -0.66
    POSITIVE LOGITS
     ago
    1.15
    days
    1.04
    pring
    0.95
     Ago
    0.93
    ilver
    0.88
    hops
    0.85
     elapsed
    0.85
    dream
    0.85
    ²¾
    0.83
    terday
    0.80
    Activations Density 0.052%

    No Known Activations